Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100697
    Prev
    Next
    INDEX
    Explanations

    code and structured text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ado
    0.46
    ك
    0.46
    ní
    0.45
    rieben
    0.45
    és
    0.44
    frame
    0.44
    Est
    0.44
    بت
    0.44
    mény
    0.44
    bol
    0.43
    POSITIVE LOGITS
     yattha
    0.53
     VII
    0.46
    辘
    0.46
     मर्
    0.45
    ską
    0.45
     apes
    0.44
     STATE
    0.44
    。)
    0.43
    ।)
    0.43
    输入的
    0.43
    Activations Density 0.000%

    No Known Activations